blazer 2.4.0 → 2.4.4

data/app/assets/stylesheets/blazer/application.css

@@ -236,3 +236,7 @@ h2 {
 .schema-table {
   max-width: 500px;
 }
+
+.selectize-dropdown .create {
+  padding: 5px 8px;
+}

data/app/controllers/blazer/queries_controller.rb

@@ -179,6 +179,7 @@ module Blazer
       if params[:commit] == "Fork"
         @query = Blazer::Query.new
         @query.creator = blazer_user if @query.respond_to?(:creator)
+        @query.status = "active" if @query.respond_to?(:status)
       end
       unless @query.editable?(blazer_user)
         @query.errors.add(:base, "Sorry, permission denied")

data/app/models/blazer/query.rb

@@ -9,7 +9,7 @@ module Blazer
     validates :statement, presence: true
 
     scope :active, -> { column_names.include?("status") ? where(status: "active") : all }
-    scope :named, -> { where("blazer_queries.name <> ''") }
+    scope :named, -> { where.not(name: "") }
 
     def to_param
       [id, name].compact.join("-").gsub("'", "").parameterize

data/lib/blazer/adapters/druid_adapter.rb

@@ -42,9 +42,9 @@ module Blazer
               end
             end
           end
-         rescue => e
-           error = e.message
-         end
+        rescue => e
+          error = e.message
+        end
 
         [columns, rows, error]
       end

data/lib/blazer/adapters/hive_adapter.rb

@@ -0,0 +1,45 @@
+module Blazer
+  module Adapters
+    class HiveAdapter < BaseAdapter
+      def run_statement(statement, comment)
+        columns = []
+        rows = []
+        error = nil
+
+        begin
+          result = client.execute("#{statement} /*#{comment}*/")
+          columns = result.any? ? result.first.keys : []
+          rows = result.map(&:values)
+        rescue => e
+          error = e.message
+        end
+
+        [columns, rows, error]
+      end
+
+      def tables
+        client.execute("SHOW TABLES").map { |r| r["tab_name"] }
+      end
+
+      def preview_statement
+        "SELECT * FROM {table} LIMIT 10"
+      end
+
+      protected
+
+      def client
+        @client ||= begin
+          uri = URI.parse(settings["url"])
+          Hexspace::Client.new(
+            host: uri.host,
+            port: uri.port,
+            username: uri.user,
+            password: uri.password,
+            database: uri.path.sub(/\A\//, ""),
+            mode: uri.scheme.to_sym
+          )
+        end
+      end
+    end
+  end
+end

data/lib/blazer/adapters/ignite_adapter.rb

@@ -0,0 +1,54 @@
+module Blazer
+  module Adapters
+    class IgniteAdapter < BaseAdapter
+      def run_statement(statement, comment)
+        columns = []
+        rows = []
+        error = nil
+
+        begin
+          result = client.query("#{statement} /*#{comment}*/", schema: default_schema, statement_type: :select, timeout: data_source.timeout)
+          columns = result.any? ? result.first.keys : []
+          rows = result.map(&:values)
+        rescue => e
+          error = e.message
+        end
+
+        [columns, rows, error]
+      end
+
+      def preview_statement
+        "SELECT * FROM {table} LIMIT 10"
+      end
+
+      def tables
+        sql = "SELECT table_schema, table_name FROM information_schema.tables WHERE table_schema NOT IN ('INFORMATION_SCHEMA', 'SYS')"
+        result = data_source.run_statement(sql)
+        result.rows.reject { |row| row[1].start_with?("__") }.map do |row|
+          (row[0] == default_schema ? row[1] : "#{row[0]}.#{row[1]}").downcase
+        end
+      end
+
+      # TODO figure out error
+      # Table `__T0` can be accessed only within Ignite query context.
+      # def schema
+      #   sql = "SELECT table_schema, table_name, column_name, data_type, ordinal_position FROM information_schema.columns WHERE table_schema NOT IN ('INFORMATION_SCHEMA', 'SYS')"
+      #   result = data_source.run_statement(sql)
+      #   result.rows.group_by { |r| [r[0], r[1]] }.map { |k, vs| {schema: k[0], table: k[1], columns: vs.sort_by { |v| v[2] }.map { |v| {name: v[2], data_type: v[3]} }} }.sort_by { |t| [t[:schema] == default_schema ? "" : t[:schema], t[:table]] }
+      # end
+
+      private
+
+      def default_schema
+        "PUBLIC"
+      end
+
+      def client
+        @client ||= begin
+          uri = URI(settings["url"])
+          Ignite::Client.new(host: uri.host, port: uri.port, username: uri.user, password: uri.password)
+        end
+      end
+    end
+  end
+end

data/lib/blazer/adapters/spark_adapter.rb

@@ -0,0 +1,9 @@
+module Blazer
+  module Adapters
+    class SparkAdapter < HiveAdapter
+      def tables
+        client.execute("SHOW TABLES").map { |r| r["tableName"] }
+      end
+    end
+  end
+end

data/lib/blazer/adapters/sql_adapter.rb

@@ -123,7 +123,7 @@ module Blazer
       end
 
       def supports_cohort_analysis?
-        postgresql?
+        postgresql? || mysql?
       end
 
       # TODO treat date columns as already in time zone
@@ -131,6 +131,27 @@ module Blazer
         raise "Cohort analysis not supported" unless supports_cohort_analysis?
 
         cohort_column = statement =~ /\bcohort_time\b/ ? "cohort_time" : "conversion_time"
+        tzname = Blazer.time_zone.tzinfo.name
+
+        if mysql?
+          time_sql = "CONVERT_TZ(cohorts.cohort_time, '+00:00', ?)"
+          case period
+          when "day"
+            date_sql = "CAST(DATE_FORMAT(#{time_sql}, '%Y-%m-%d') AS DATE)"
+            date_params = [tzname]
+          when "week"
+            date_sql = "CAST(DATE_FORMAT(#{time_sql} - INTERVAL ((5 + DAYOFWEEK(#{time_sql})) % 7) DAY, '%Y-%m-%d') AS DATE)"
+            date_params = [tzname, tzname]
+          else
+            date_sql = "CAST(DATE_FORMAT(#{time_sql}, '%Y-%m-01') AS DATE)"
+            date_params = [tzname]
+          end
+          bucket_sql = "CAST(CEIL(TIMESTAMPDIFF(SECOND, cohorts.cohort_time, query.conversion_time) / ?) AS INTEGER)"
+        else
+          date_sql = "date_trunc(?, cohorts.cohort_time::timestamptz AT TIME ZONE ?)::date"
+          date_params = [period, tzname]
+          bucket_sql = "CEIL(EXTRACT(EPOCH FROM query.conversion_time - cohorts.cohort_time) / ?)::int"
+        end
 
         # WITH not an optimization fence in Postgres 12+
         statement = <<~SQL
@@ -143,14 +164,14 @@ module Blazer
             GROUP BY 1
           )
           SELECT
-            date_trunc(?, cohorts.cohort_time::timestamptz AT TIME ZONE ?)::date AS period,
+            #{date_sql} AS period,
             0 AS bucket,
             COUNT(DISTINCT cohorts.user_id)
           FROM cohorts GROUP BY 1
           UNION ALL
           SELECT
-            date_trunc(?, cohorts.cohort_time::timestamptz AT TIME ZONE ?)::date AS period,
-            CEIL(EXTRACT(EPOCH FROM query.conversion_time - cohorts.cohort_time) / ?)::int AS bucket,
+            #{date_sql} AS period,
+            #{bucket_sql} AS bucket,
             COUNT(DISTINCT query.user_id)
           FROM cohorts INNER JOIN query ON query.user_id = cohorts.user_id
           WHERE query.conversion_time IS NOT NULL
@@ -158,8 +179,7 @@ module Blazer
           #{cohort_column == "conversion_time" ? "AND query.conversion_time != cohorts.cohort_time" : ""}
           GROUP BY 1, 2
         SQL
-        tzname = Blazer.time_zone.tzinfo.name
-        params = [statement, period, tzname, period, tzname, days.to_i * 86400]
+        params = [statement] + date_params + date_params + [days.to_i * 86400]
         connection_model.send(:sanitize_sql_array, params)
       end
 
@@ -206,6 +226,8 @@ module Blazer
             "public"
           elsif sqlserver?
             "dbo"
+          elsif connection_model.respond_to?(:connection_db_config)
+            connection_model.connection_db_config.database
           else
             connection_model.connection_config[:database]
           end

data/lib/blazer/data_source.rb

@@ -144,6 +144,7 @@ module Blazer
 
     def adapter_instance
       @adapter_instance ||= begin
+        # TODO add required settings to adapters
         unless settings["url"] || Rails.env.development? || ["bigquery", "athena", "snowflake", "salesforce"].include?(settings["adapter"])
           raise Blazer::Error, "Empty url for data source: #{id}"
         end
@@ -182,11 +183,12 @@ module Blazer
       Blazer::Result.new(self, columns, rows, error, nil, cache && !cache_data.nil?)
     end
 
+    # TODO check for adapter with same name, default to sql
     def detect_adapter
-      schema = settings["url"].to_s.split("://").first
-      case schema
-      when "mongodb", "presto", "cassandra"
-        schema
+      scheme = settings["url"].to_s.split("://").first
+      case scheme
+      when "mongodb", "presto", "cassandra", "ignite"
+        scheme
       else
         "sql"
       end

data/lib/blazer/result.rb

@@ -174,7 +174,19 @@ module Blazer
     def anomaly?(series)
       series = series.reject { |v| v[0].nil? }.sort_by { |v| v[0] }
 
-      if Blazer.anomaly_checks == "trend"
+      case Blazer.anomaly_checks
+      when "prophet"
+        df = Rover::DataFrame.new(series[0..-2].map { |v| {"ds" => v[0], "y" => v[1]} })
+        m = Prophet.new(interval_width: 0.99)
+        m.logger.level = ::Logger::FATAL # no logging
+        m.fit(df)
+        future = Rover::DataFrame.new(series[-1..-1].map { |v| {"ds" => v[0]} })
+        forecast = m.predict(future).to_a[0]
+        lower = forecast["yhat_lower"]
+        upper = forecast["yhat_upper"]
+        value = series.last[1]
+        value < lower || value > upper
+      when "trend"
         anomalies = Trend.anomalies(Hash[series])
         anomalies.include?(series.last[0])
       else

data/lib/blazer/version.rb

@@ -1,3 +1,3 @@
 module Blazer
-  VERSION = "2.4.0"
+  VERSION = "2.4.4"
 end

data/lib/blazer.rb

@@ -18,12 +18,15 @@ require "blazer/adapters/cassandra_adapter"
 require "blazer/adapters/drill_adapter"
 require "blazer/adapters/druid_adapter"
 require "blazer/adapters/elasticsearch_adapter"
+require "blazer/adapters/hive_adapter"
+require "blazer/adapters/ignite_adapter"
 require "blazer/adapters/influxdb_adapter"
 require "blazer/adapters/mongodb_adapter"
 require "blazer/adapters/neo4j_adapter"
 require "blazer/adapters/presto_adapter"
 require "blazer/adapters/salesforce_adapter"
 require "blazer/adapters/soda_adapter"
+require "blazer/adapters/spark_adapter"
 require "blazer/adapters/sql_adapter"
 require "blazer/adapters/snowflake_adapter"
 
@@ -239,11 +242,14 @@ Blazer.register_adapter "cassandra", Blazer::Adapters::CassandraAdapter
 Blazer.register_adapter "drill", Blazer::Adapters::DrillAdapter
 Blazer.register_adapter "druid", Blazer::Adapters::DruidAdapter
 Blazer.register_adapter "elasticsearch", Blazer::Adapters::ElasticsearchAdapter
+Blazer.register_adapter "hive", Blazer::Adapters::HiveAdapter
+Blazer.register_adapter "ignite", Blazer::Adapters::IgniteAdapter
 Blazer.register_adapter "influxdb", Blazer::Adapters::InfluxdbAdapter
 Blazer.register_adapter "neo4j", Blazer::Adapters::Neo4jAdapter
 Blazer.register_adapter "presto", Blazer::Adapters::PrestoAdapter
 Blazer.register_adapter "mongodb", Blazer::Adapters::MongodbAdapter
 Blazer.register_adapter "salesforce", Blazer::Adapters::SalesforceAdapter
 Blazer.register_adapter "soda", Blazer::Adapters::SodaAdapter
+Blazer.register_adapter "spark", Blazer::Adapters::SparkAdapter
 Blazer.register_adapter "sql", Blazer::Adapters::SqlAdapter
 Blazer.register_adapter "snowflake", Blazer::Adapters::SnowflakeAdapter

data/lib/generators/blazer/templates/config.yml.tt

@@ -63,11 +63,11 @@ check_schedules:
 
 # enable anomaly detection
 # note: with trend, time series are sent to https://trendapi.org
-# anomaly_checks: trend / r
+# anomaly_checks: prophet / trend / r
 
 # enable forecasting
 # note: with trend, time series are sent to https://trendapi.org
-# forecasting: trend / prophet
+# forecasting: prophet / trend
 
 # enable map
 # mapbox_access_token: <%%= ENV["MAPBOX_ACCESS_TOKEN"] %>

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: blazer
 version: !ruby/object:Gem::Version
-  version: 2.4.0
+  version: 2.4.4
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-12-15 00:00:00.000000000 Z
+date: 2021-09-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: railties
@@ -66,36 +66,8 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 0.1.1
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 description:
-email: andrew@chartkick.com
+email: andrew@ankane.org
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -194,6 +166,8 @@ files:
 - lib/blazer/adapters/drill_adapter.rb
 - lib/blazer/adapters/druid_adapter.rb
 - lib/blazer/adapters/elasticsearch_adapter.rb
+- lib/blazer/adapters/hive_adapter.rb
+- lib/blazer/adapters/ignite_adapter.rb
 - lib/blazer/adapters/influxdb_adapter.rb
 - lib/blazer/adapters/mongodb_adapter.rb
 - lib/blazer/adapters/neo4j_adapter.rb
@@ -201,6 +175,7 @@ files:
 - lib/blazer/adapters/salesforce_adapter.rb
 - lib/blazer/adapters/snowflake_adapter.rb
 - lib/blazer/adapters/soda_adapter.rb
+- lib/blazer/adapters/spark_adapter.rb
 - lib/blazer/adapters/sql_adapter.rb
 - lib/blazer/data_source.rb
 - lib/blazer/detect_anomalies.R
@@ -250,7 +225,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.4
+rubygems_version: 3.2.22
 signing_key:
 specification_version: 4
 summary: Explore your data with SQL. Easily create charts and dashboards, and share